Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 5990
    Prev
    Next
    INDEX
    Explanations

    associated colors and shades, particularly black and dark tones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.71
     Theſe
    -0.69
    =$?
    -0.67
     daisy
    -0.64
    ſelf
    -0.63
    avoit
    -0.62
     Margar
    -0.62
     justifyContent
    -0.61
     ſche
    -0.60
    NameInMap
    -0.59
    POSITIVE LOGITS
     dark
    1.27
     Dark
    1.14
     blackness
    1.14
     black
    1.14
     darkest
    1.12
    Darkness
    1.12
     darken
    1.11
    dark
    1.09
    Dark
    1.09
     darker
    1.09
    Activations Density 0.935%

    No Known Activations